Metadata-Version: 2.1
Name: kaggle-fastai-custom-metrics
Version: 1.0.2
Summary: Custom Metrics for fastai v1 for kaggle competitions
Home-page: https://shadabsayeed.tech/2020-09-08-CustomMetrics/
Author: shadab_sayeed
Author-email: shadabsayeedxxx@gmail.com
License: MIT
Download-URL: https://github.com/shadab4150/kaggle_fastai_custom_metrics/archive/v1.0.2.tar.gz
Description: # kaggle fastai custom metrics
        ***
        
        Custom Metrics for fastai v1 for kaggle competitions.
        
        ***
        ## Disclaimer :
        
        Each Kaggle competition has a unique metrics suited to its, need this package lets you download those custom metrics to be used with fastai library.
        Since Metrics are an important part to evaulate your models performance.
        
        ## Installation 
        
        ```sh
        pip install kaggle-fastai-custom-metrics==1.0.2
        ```
        
        or
        
        ```bash
        git clone https://github.com/shadab4150/kaggle_fastai_custom_metrics
        cd kaggle_fastai_custom_metrics
        pip install .
        ```
        ## Usage :
        
        ```python
        from kaggle_fastai_custom_metrics.kfcm import *
        print_all_metrics()
        ```
        <table style="width:100%">
          <tr>
            <th>Competition URL</th>
            <th>Metric</th> 
          </tr>
          <tr>
            <td>https://www.kaggle.com/c/plant-pathology-2020-fgvc7</td>
            <td>column_mean_logloss</td>
          </tr>
          <tr>
            <td>https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge</td>
            <td>column_mean_aucroc</td>
          </tr>
          <tr>
            <td>https://www.kaggle.com/c/trends-assessment-prediction</td>
            <td>weighted_mae</td>
          </tr>
           <tr>
            <td> https://www.kaggle.com/c/alaska2-image-steganalysis</td>
            <td>alaska_weighted_auc</td>
          </tr>
           <tr>
            <td>https://www.kaggle.com/c/google-quest-challenge</td>
            <td>AvgSpearman</td>
          </tr>
          <tr>
            <td>https://www.kaggle.com/c/landmark-recognition-2020</td>
            <td>GAP_vector</td>
          </tr>
          <tr>
            </table>
        
        ```
        metric = weighted_auc();
        learn = Learner(data, arch, metrics= [metric] );
        ```
        
Keywords: Fastai,Competition Metrics,Kaggle
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
